A novel partially occluded face recognition method based on biomimetic pattern recognition

Author

Zeng, Jun-ying ; Gan, Jun-ying ; Zhai, Yi-kui

Author_Institution

Sch. of Inf. Eng., Wu Yi Univ., Jiangmen, China

fYear

2012

fDate

15-17 July 2012

Firstpage

175

Lastpage

179

Abstract

A novel partially occluded face recognition method based on biomimetic pattern recognition (BPR), proposed by academician Shoujue Wang, is proposed in this paper. A model for partially occluded face recognition based on BPR was introduced. An experiment based on biomimetic pattern recognition adopting a PCA and LDA feature extraction method is performed. Experimental results on Yale image database demonstrate that the use of Biomimetic Pattern Recognition makes it possible to achieve highly accurate and efficient recognition results with the proposed partially occluded face recognition model.

Keywords

face recognition; feature extraction; principal component analysis; visual databases; BPR; LDA feature extraction method; PCA; Yale image database; biomimetic pattern recognition; partially occluded face recognition method; Business process re-engineering; Face; Face recognition; Principal component analysis; Training; Vectors; Biomimetic Pattern Recognition; Occluded Face Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Wavelet Analysis and Pattern Recognition (ICWAPR), 2012 International Conference on

Conference_Location

Xian

ISSN

2158-5695

Print_ISBN

978-1-4673-1534-0

Type

conf

DOI

10.1109/ICWAPR.2012.6294774

Filename

6294774